Verified:GitHub

/prefill

Generate slugged wiki foundation pages from Wikipedia or LLM definitions.

77|16|Updated May 9, 2026

Search Tags:#deduplication #yaml frontmatter #foundations #research workflow #domain taxonomy #wikipedia ingestion #wiki prefill

Ready to run

npx skills add https://github.com/Lambenthan/empiricalwiki --skill prefill-lambenthan

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: /prefill
Source: https://github.com/Lambenthan/empiricalwiki/tree/main/.claude/skills/prefill
Command: npx skills add https://github.com/Lambenthan/empiricalwiki --skill prefill-lambenthan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents your wiki from generating duplicate, textbook-style concept pages by pre-filling foundational knowledge for a given research domain in a controlled, terminal-only way.

Core Features & Use Cases

Foundation seeding with deduplication: Creates wiki/foundations/{slug}.md only if it doesn’t already exist, never overwriting existing pages.
Domain inference + targeted addition: Uses an explicit domain, or infers it from wiki/topics/*.md tags, or supports --add "概念名" to seed a single foundation directly.
Wikipedia-backed definitions: Fetches summaries and structured sections from Wikipedia (with graceful fallback to LLM knowledge when a page is missing).

Quick Start

Ask the assistant to run: /prefill NLP.

Frequently Asked Questions about /prefill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I prevent duplicate concept pages when seeding a research wiki?▼

To prevent duplicate concept pages when seeding a research wiki, use a prefill workflow that performs idempotent writes. It generates slugged foundation pages from templates only if they do not already exist, ensuring consistent foundational terminology without overwriting prior definitions.

How does Wikipedia ingestion work for building wiki foundations?▼

Wikipedia ingestion for building wiki foundations fetches summaries and structured sections to create definition pages. When a specific Wikipedia page is missing, the process uses a graceful fallback to LLM-derived knowledge to maintain domain coverage.

Can I seed a single concept page instead of an entire research domain?▼

Yes, you can seed a single concept page instead of an entire domain by using a targeted addition command. This allows manual prefill of individual slugged foundation pages directly, while still updating the wiki index and logs.

Do I need to specify a domain taxonomy manually for the prefill process?▼

No, you do not need to specify a domain taxonomy manually for the prefill process. The system can use an explicit domain, or it can automatically infer the domain by reading topic tags from existing wiki topics files.

What happens to existing markdown files when pre-filling foundational knowledge?▼

Existing markdown files are completely protected when pre-filling foundational knowledge. The process strictly avoids duplicate concept pages by checking for existing files and never overwriting them, ensuring your current wiki foundations remain unchanged.